Image-based disease detection and classification in Indian apple plant species by using deep learning

Abstract

Plant diseases are a major threat to food security, but their rapid identification remains difficult in many parts of the world due to the lack of the necessary infrastructure. Traditional farming methods are insufficient to address the impending global food crises. As a result, agricultural productivity growth is critical, and new techniques and methods are required for efficient and sustainable farming practices that balance the supply chain according to customer demand. Even though India is one of the most agriculturally dependent countries, it nevertheless suffers from various agricultural shortages. Plant diseases that go unnoticed and untreated are one such deprivation. Developing an intelligent automated technique for plant disease detection is explored in this research. Deep learning is used to create a smart system for image-based disease detection in Indian apple plant species. Specifically, this study uses a convolution neural network architecture, ResNet-34, to identify diseases in apple plants. Based on 70-30% and 80-20% dataset partition, the proposed model obtained an accuracy of 97.5% and 98.4%, respectively. The results obtained from this study illustrate the productive exploration and utility of the proposed model for future research by implementing various deep learning models and incorporating additional modules that provide cure and preventative measures for the detected diseases.